Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    began, began with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     എത്ത
    0.42
    作出
    0.42
     เนาะ
    0.41
    ndet
    0.40
    𝘮
    0.39
    주시
    0.38
     निकालते
    0.38
     nowrap
    0.37
    ومة
    0.37
    étera
    0.37
    POSITIVE LOGITS
    導致
    0.48
     caused
    0.46
     began
    0.45
    caused
    0.44
     Beginning
    0.43
    begin
    0.43
     causing
    0.41
     カテゴ
    0.41
     Begin
    0.41
     supere
    0.40
    Act Density 0.000%

    No Known Activations